Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2604 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.5474. Min Act: -0.0000

Data Index: 1593363 (The Pile)

Max Activating Token Index: 932

Text #1

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.5764. Min Act: -0.0000

Data Index: 1343978 (The Pile)

Max Activating Token Index: 581

Text #2

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.5150. Min Act: -0.0000

Data Index: 1983509 (The Pile)

Max Activating Token Index: 679

Text #3

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.5317. Min Act: -0.0000

Data Index: 639641 (The Pile)

Max Activating Token Index: 917

Text #4

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.4942. Min Act: -0.0000

Data Index: 1660868 (The Pile)

Max Activating Token Index: 962

Text #5

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.5624. Min Act: -0.0000

Data Index: 876523 (The Pile)

Max Activating Token Index: 887

Text #6

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.5236. Min Act: -0.0000

Data Index: 323826 (The Pile)

Max Activating Token Index: 945

Text #7

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.5690. Min Act: -0.0000

Data Index: 1617331 (The Pile)

Max Activating Token Index: 88

Text #8

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.5381. Min Act: -0.0000

Data Index: 1351552 (The Pile)

Max Activating Token Index: 152

Text #9

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.5363. Min Act: -0.0000

Data Index: 760289 (The Pile)

Max Activating Token Index: 460

Text #10

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.5357. Min Act: -0.0000

Data Index: 615230 (The Pile)

Max Activating Token Index: 930

Text #11

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.5251. Min Act: -0.0000

Data Index: 1210327 (The Pile)

Max Activating Token Index: 761

Text #12

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.5094. Min Act: -0.0000

Data Index: 1067707 (The Pile)

Max Activating Token Index: 537

Text #13

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.5002. Min Act: -0.0000

Data Index: 1005845 (The Pile)

Max Activating Token Index: 884

Text #14

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.4826. Min Act: -0.0000

Data Index: 1759886 (The Pile)

Max Activating Token Index: 95

Text #15

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.4845. Min Act: -0.0000

Data Index: 72876 (The Pile)

Max Activating Token Index: 940

Text #16

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.4920. Min Act: -0.0000

Data Index: 1716360 (The Pile)

Max Activating Token Index: 848

Text #17

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.5404. Min Act: -0.0000

Data Index: 1577057 (The Pile)

Max Activating Token Index: 282

Text #18

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.5701. Min Act: -0.0000

Data Index: 1153884 (The Pile)

Max Activating Token Index: 820

Text #19

Max Range: 0.5764. Min Range: -0.5764

Max Act: 0.4951. Min Act: -0.0000

Data Index: 1071766 (The Pile)

Max Activating Token Index: 852